Commit Graph

217 Commits

Author SHA1 Message Date
Niall Coates
4ffc7a17d4
server : various fixes for the prompt field in /completion (#5300)
server : fix deadlock when prompt array contains strings and numbers

server : removed an unnecessary generation when generating multi-prompts

server : removed an unnecessary assert
2024-02-06 10:16:23 +02:00
Alexey Parfenov
a2d60c9158
server : allow to get default generation settings for completion (#5307) 2024-02-05 10:10:22 +02:00
Michael Klimenko
52bb63c708
refactor : switch to emplace_back to avoid extra object (#5291) 2024-02-03 13:23:37 +02:00
Georgi Gerganov
5cb04dbc16
llama : remove LLAMA_MAX_DEVICES and LLAMA_SUPPORTS_GPU_OFFLOAD (#5240)
* llama : remove LLAMA_MAX_DEVICES from llama.h

ggml-ci

* Update llama.cpp

Co-authored-by: slaren <slarengh@gmail.com>

* server : remove LLAMA_MAX_DEVICES

ggml-ci

* llama : remove LLAMA_SUPPORTS_GPU_OFFLOAD

ggml-ci

* train : remove LLAMA_SUPPORTS_GPU_OFFLOAD

* readme : add deprecation notice

* readme : change deprecation notice to "remove" and fix url

* llama : remove gpu includes from llama.h

ggml-ci

---------

Co-authored-by: slaren <slarengh@gmail.com>
2024-01-31 17:30:17 +02:00
Georgi Gerganov
e0085fdf7c
Revert "server : change deps.sh xxd files to string literals (#5221)"
This reverts commit 4003be0e5f.
2024-01-30 21:19:26 +02:00
Georgi Gerganov
e6f291d158
server : fix context shift (#5195)
* server : fix context shift + simplify self-extend

* server : take system_tokens into account

* server : more n_past fixes

* server : rever n_past_se changes
2024-01-30 20:17:30 +02:00
JohnnyB
4003be0e5f
server : change deps.sh xxd files to string literals (#5221)
* Changed ugly xxd to literals.

HPP files are much more readable as multiline literals rather than hex arrays.

* Dashes in literal variable names.

Replace . and - with _ in file names -> variable names.

* Comment on removing xxd.

XXD-> string literals

* XXD to string literals.

Replaced these unreadable headers with string literal versions using new deps.sh.
2024-01-30 20:15:05 +02:00
Wu Jian Ping
6685cc41c2
server : improve README (#5209) 2024-01-30 11:11:46 +02:00
Wu Jian Ping
c82d18e863
server : embeddings compatibility for OpenAI (#5190) 2024-01-29 15:48:10 +02:00
Abhilash Majumder
0f648573dd
ggml : add unified SYCL backend for Intel GPUs (#2690)
* first update for migration

* update init_cublas

* add debug functio, commit all help code

* step 1

* step 2

* step3 add fp16, slower 31->28

* add GGML_LIST_DEVICE function

* step 5 format device and print

* step6, enhance error check, remove CUDA macro, enhance device id to fix none-zero id issue

* support main device is non-zero

* step7 add debug for code path, rm log

* step 8, rename all macro & func from cuda by sycl

* fix error of select non-zero device, format device list

* ren ggml-sycl.hpp -> ggml-sycl.h

* clear CMAKE to rm unused lib and options

* correct queue: rm dtct:get_queue

* add print tensor function to debug

* fix error: wrong result in 658746bb26702e50f2c59c0e4ada8e9da6010481

* summary dpct definition in one header file to replace folder:dpct

* refactor device log

* mv dpct definition from folder dpct to ggml-sycl.h

* update readme, refactor build script

* fix build with sycl

* set nthread=1 when sycl, increase performance

* add run script, comment debug code

* add ls-sycl-device tool

* add ls-sycl-device, rm unused files

* rm rear space

* dos2unix

* Update README_sycl.md

* fix return type

* remove sycl version from include path

* restore rm code to fix hang issue

* add syc and link for sycl readme

* rm original sycl code before refactor

* fix code err

* add know issue for pvc hang issue

* enable SYCL_F16 support

* align pr4766

* check for sycl blas, better performance

* cleanup 1

* remove extra endif

* add build&run script, clean CMakefile, update guide by review comments

* rename macro to intel hardware

* editor config format

* format fixes

* format fixes

* editor format fix

* Remove unused headers

* skip build sycl tool for other code path

* replace tab by space

* fix blas matmul function

* fix mac build

* restore hip dependency

* fix conflict

* ren as review comments

* mv internal function to .cpp file

* export funciton print_sycl_devices(), mv class dpct definition to source file

* update CI/action for sycl code, fix CI error of repeat/dup

* fix action ID format issue

* rm unused strategy

* enable llama_f16 in ci

* fix conflict

* fix build break on MacOS, due to CI of MacOS depend on external ggml, instead of internal ggml

* fix ci cases for unsupported data type

* revert unrelated changed in cuda cmake
remove useless nommq
fix typo of GGML_USE_CLBLAS_SYCL

* revert hip cmake changes

* fix indent

* add prefix in func name

* revert no mmq

* rm cpu blas duplicate

* fix no_new_line

* fix src1->type==F16 bug.

* pass batch offset for F16 src1

* fix batch error

* fix wrong code

* revert sycl checking in test-sampling

* pass void as arguments of ggml_backend_sycl_print_sycl_devices

* remove extra blank line in test-sampling

* revert setting n_threads in sycl

* implement std::isinf for icpx with fast math.

* Update ci/run.sh

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update examples/sycl/run-llama2.sh

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update examples/sycl/run-llama2.sh

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update CMakeLists.txt

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update CMakeLists.txt

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update CMakeLists.txt

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update CMakeLists.txt

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* add copyright and MIT license declare

* update the cmd example

---------

Co-authored-by: jianyuzh <jianyu.zhang@intel.com>
Co-authored-by: luoyu-intel <yu.luo@intel.com>
Co-authored-by: Meng, Hengyu <hengyu.meng@intel.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-28 17:56:23 +02:00
Kyle Mistele
39baaf55a1
docker : add server-first container images (#5157)
* feat: add Dockerfiles for each platform that user ./server instead of ./main

* feat: update .github/workflows/docker.yml to build server-first docker containers

* doc: add information about running the server with Docker to README.md

* doc: add information about running with docker to the server README

* doc: update n-gpu-layers to show correct GPU usage

* fix(doc): update container tag from `server` to `server-cuda` for README example on running server container with CUDA
2024-01-28 09:55:31 +02:00
Georgi Gerganov
753eafed0e
sync : ggml 2024-01-27 17:00:24 +02:00
Michael Klimenko
35a2ee9143
Remove unused data and add fixes (#5154)
* Remove unused data and add fixes

* Add missing file

* Address review comments

* Replace the scope of vq allocation
2024-01-27 15:25:55 +01:00
Maximilian Winter
ec903c0341
server : add self-extend support (#5104)
* Ported self extension to server example

* Update server.cpp

* Fixed prompt caching without self extend

* Update server.cpp

* Added description to server readme.

* Update server.cpp

* Update server.cpp

* Update server.cpp

* Update server.cpp

* Update README.md

* Changed descriptions

* server : formatting

* Update examples/server/server.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update examples/server/server.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update server.cpp

* Update server.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-27 15:38:05 +02:00
Xuan Son Nguyen
48c857aa10
server : refactored the task processing logic (#5065)
* server: add llama_server_queue struct

* server: add llama_server_response_event

* server: add comments

* server: move all mutexes away from server.cpp

* server: correct multitask response

* server: only add back deferred tasks when one slot is available

* server: fix a race condition cause by "request_completion"
2024-01-26 14:42:20 +02:00
Xuan Son Nguyen
821f0a271e
server : defer tasks when "slot unavailable" (#5018)
* server: defer task when no slot is available

* remove unnecessary log

---------

Co-authored-by: Xuan Son Nguyen <xuanson.nguyen@snowpack.eu>
2024-01-18 22:33:05 +02:00
Georgi Gerganov
0ea069b87b
server : fix prompt caching with system prompt (#4914) 2024-01-13 19:31:26 +02:00
Ziad Ben Hadj-Alouane
356327feb3
server : fix deadlock that occurs in multi-prompt scenarios (#4905)
* * fix deadlock

* * dont ruint all whitespace
2024-01-13 16:20:46 +02:00
makomk
ee8243adaa
server : fix crash with multimodal models without BOS token (#4904) 2024-01-13 16:16:11 +02:00
slaren
e7e4df031b
llama : ggml-backend integration (#4766)
* llama : ggml-backend integration

* ggml-backend : add names to buffers

* fix unmap after loading

* batched-bench : add tensor_split param

* llama : check for null tensor_split

* ggml-backend : increase GGML_MAX_BACKENDS

* improve graph splitting, partial fix for --no-kv-offload

* cuda : add ggml-backend split buffer support

* cuda : do not create buffer types for devices that don't exist (fixes usage without CUDA devices available)

* ggml : fix null backend dereference (#4807)

* ggml : fix null backend dereference

* ggml : also check ggml_backend_is_cpu

* test-backend-ops : check buffer allocation failures

* llama : add cparam (split_mode) and command line argument (--split-mode, -sm) to configure the split mode (none, layer or row)

* ggml : fix mul_mat_id work size

* llama : rewrite session kv load/set without graphs

* minor

* llama : only initialize used backends, free backends on context free

* llama : abort ctx if cuda backend init fails

* llama : rewrite lora with ggml-backend and compute on CPU

ggml-ci

* llama : only map to a backend buffer the region of the file mapping containing the tensors used in the buffer

* opencl : add ggml-backend buffer type

* cuda : only use batched_cublas with batched mat muls (fixes fp16 tg perf)

* llama : on Metal, by default offload the full model

ggml-ci

* metal : page align the data ptr (#4854)

* Apply suggestions from code review

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* cuda : fix split buffer free

* address review comments

* llama-bench : add split-mode parameter

* fix whitespace

* opencl : fix double initialization

* server : add --split-mode parameter

* use async copy and compute to improve multi-gpu performance

ggml-ci

* use async memcpys to copy the graph outputs to the CPU

* fix opencl

* use a host buffer for the cpu compute buffer for faster copies to the gpu

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
2024-01-12 20:07:38 +01:00
Georgi Gerganov
1d118386fe
server : fix infill when prompt is empty (#4833) 2024-01-11 23:23:49 +02:00
Laura
4330bd83fe
server : implement credentialed CORS (#4514)
* Implement credentialed CORS according to MDN

* Fix syntax error

* Move validate_api_key up so it is defined before its first usage
2024-01-11 20:02:48 +02:00
Michael Coppola
27379455c3
server : support for multiple api keys (#4864)
* server: added support for multiple api keys, added loading api keys from file

* minor: fix whitespace

* added file error handling to --api-key-file, changed code to better
reflect current style

* server: update README.md for --api-key-file

---------

Co-authored-by: Michael Coppola <info@michaeljcoppola.com>
2024-01-11 19:51:17 +02:00
Behnam M
eab6795006
server : add LOG_INFO when model is successfully loaded (#4881)
* added /health endpoint to the server

* added comments on the additional /health endpoint

* Better handling of server state

When the model is being loaded, the server state is `LOADING_MODEL`. If model-loading fails, the server state becomes `ERROR`, otherwise it becomes `READY`. The `/health` endpoint provides more granular messages now according to the server_state value.

* initialized server_state

* fixed a typo

* starting http server before initializing the model

* Update server.cpp

* Update server.cpp

* fixes

* fixes

* fixes

* made ServerState atomic and turned two-line spaces into one-line

* updated `server` readme to document the `/health` endpoint too

* used LOG_INFO after successful model loading
2024-01-11 19:41:39 +02:00
Isaac McFadyen
2f043328e3
server : fix typo in model name (#4876) 2024-01-11 16:33:26 +02:00
Behnam M
7a9f75c38b
server : update readme to document the new /health endpoint (#4866)
* added /health endpoint to the server

* added comments on the additional /health endpoint

* Better handling of server state

When the model is being loaded, the server state is `LOADING_MODEL`. If model-loading fails, the server state becomes `ERROR`, otherwise it becomes `READY`. The `/health` endpoint provides more granular messages now according to the server_state value.

* initialized server_state

* fixed a typo

* starting http server before initializing the model

* Update server.cpp

* Update server.cpp

* fixes

* fixes

* fixes

* made ServerState atomic and turned two-line spaces into one-line

* updated `server` readme to document the `/health` endpoint too
2024-01-11 09:12:05 +02:00
Georgi Gerganov
5c1980d8d4
server : fix build + rename enums (#4870) 2024-01-11 09:10:34 +02:00
Behnam M
cd108e641d
server : add a /health endpoint (#4860)
* added /health endpoint to the server

* added comments on the additional /health endpoint

* Better handling of server state

When the model is being loaded, the server state is `LOADING_MODEL`. If model-loading fails, the server state becomes `ERROR`, otherwise it becomes `READY`. The `/health` endpoint provides more granular messages now according to the server_state value.

* initialized server_state

* fixed a typo

* starting http server before initializing the model

* Update server.cpp

* Update server.cpp

* fixes

* fixes

* fixes

* made ServerState atomic and turned two-line spaces into one-line
2024-01-10 21:56:05 +02:00
Behnam M
128de3585b
server : update readme about token probs (#4777)
* updated server readme to reflect the gg/server-token-probs-4088 commit

added explanation for the API's completion result which now includes `completion_probabilities`. Also added a JSON schema that shows the type/structure of `completion_probabilities`.

* simplified the `completion_probabilities` JSON schema 

It's now easier to understand what the structure of `completion_probabilities` looks like.

* minor : fix trailing whitespace

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-09 12:02:05 +02:00
Zsapi
8c58330318
server : add api-key flag to documentation (#4832)
Document the api-key flag added to server in https://github.com/ggerganov/llama.cpp/pull/4441
2024-01-09 11:12:43 +02:00
Georgi Gerganov
67984921a7
server : fix n_predict check (#4798) 2024-01-07 08:45:26 +02:00
Georgi Gerganov
012cf349ae
server : send token probs for "stream == false" (#4714) 2024-01-04 19:56:33 +02:00
Michael Coppola
e5804313a1
server : fix options in README.md (#4765)
* fix examples/server/README.md

* minor : fix whitespace

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-04 10:17:09 +02:00
Justin Parker
f2eb19bd8b
server : throw an error when slot unavailable (#4741) 2024-01-03 10:43:19 +02:00
Phil H
0ef3ca2ac6
server : add token counts to html footer (#4738)
* server: add token counts to stats

* server: generate hpp

---------

Co-authored-by: phiharri <ph@got-root.co.uk>
2024-01-02 17:48:49 +02:00
Georgi Gerganov
32866c5edd
editorconfig : fix whitespace and indentation #4710 2024-01-02 13:28:15 +02:00
minarchist
5d7002d437
server : add --override-kv parameter (#4710)
* Changes to server to allow metadata override

* documentation

* flake.nix: expose full scope in legacyPackages

* flake.nix: rocm not yet supported on aarch64, so hide the output

* flake.nix: expose checks

* workflows: nix-ci: init; build flake outputs

* workflows: nix-ci: add a job for eval

* workflows: weekly `nix flake update`

* workflows: nix-flakestry: drop tag filters

...and add a job for flakehub.com

* workflows: nix-ci: add a qemu job for jetsons

* flake.nix: suggest the binary caches

* flake.lock: update

to a commit recently cached by nixpkgs-cuda-ci

---------

Co-authored-by: John <john@jLap.lan>
Co-authored-by: Someone Serge <sergei.kozlukov@aalto.fi>
2024-01-02 12:38:15 +02:00
Georgi Gerganov
9fbda719de
clip : refactor + bug fixes (#4696)
* clip : refactor + bug fixes

ggml-ci

* server : add log message
2023-12-30 23:24:42 +02:00
Cuong Trinh Manh
97bbca6e85
cmake : fix ld warning duplicate libraries libllama.a (#4671)
* fix "ld: warning: ignoring duplicate libraries: '../libllama.a'"

* fix warning in example.
2023-12-29 16:39:15 +02:00
Justine Tunney
db49ff8ed7
server : replace sleep with condition variables (#4673)
The server currently schedules tasks using a sleep(5ms) busy loop. This
adds unnecessary latency since most sleep implementations do a round up
to the system scheduling quantum (usually 10ms). Other libc sleep impls
spin for smaller time intervals which results in the server's busy loop
consuming all available cpu. Having the explicit notify() / wait() code
also helps aid in the readability of the server code.

See mozilla-Ocho/llamafile@711344b
2023-12-29 16:24:12 +02:00
SakuraUmi
60f55e888c
server : fix OpenAI server sampling w.r.t. penalty. (#4675) 2023-12-29 16:22:44 +02:00
Karthik Sethuraman
b93edd22f5
server : allow to generate multimodal embeddings (#4681) 2023-12-29 16:22:10 +02:00
Justine Tunney
65e5f6dadb
Fix OpenAI server sampling w.r.t. temp and seed (#4668)
The default values for tfs_z and typical_p were being set to zero, which
caused the token candidates array to get shrunk down to one element thus
preventing any sampling. Note this only applies to OpenAI API compatible
HTTP server requests.

The solution is to use the default values that OpenAI documents, as well
as ensuring we use the llama.cpp defaults for the rest. I've tested this
change still ensures deterministic output by default. If a "temperature"
greater than 0 is explicitly passed, then output is unique each time. If
"seed" is specified in addition to "temperature" then the output becomes
deterministic once more.

See mozilla-Ocho/llamafile#117
See mozilla-Ocho/llamafile@9e4bf29
2023-12-28 15:20:00 -04:00
Alexey Parfenov
6123979952
server : allow to specify custom prompt for penalty calculation (#3727) 2023-12-23 11:31:49 +02:00
olexiyb
0ffc92d2d2
server : disable llm logs if SERVER_VERBOSE is off (#3792) 2023-12-17 17:02:16 +02:00
AdithyanI
8edd2b40fd
server : fix grammar being ignored (#4494)
Fix bug in identifying the grammar.
2023-12-17 16:57:56 +02:00
Alexey Parfenov
eb16dae7e7
server : fix possible ambiguity in content type charset (#4501) 2023-12-17 16:56:09 +02:00
mzcu
62bd52b7bf
server : allow requests larger than 8K (#4500) 2023-12-17 16:54:37 +02:00
ShadovvBeast
88ae8952b6
server : add optional API Key Authentication example (#4441)
* Add API key authentication for enhanced server-client security

* server : to snake_case

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-12-15 13:49:01 +02:00
shibe2
948ff137ec
server : fix handling of characters that span multiple tokens when streaming (#4446) 2023-12-13 21:57:15 +02:00
kalomaze
fecac45658
server : tweak default sampling parameters (#4367)
* Set a more typical Top P setting as the default

* Update temp max
2023-12-12 12:12:35 +02:00
Richard Kiss
9494d7c477
english : use typos to fix comments and logs (#4354) 2023-12-12 11:53:36 +02:00
Vladimir Zorin
d9d4cfef64
server : fix local model name in server (#4420) 2023-12-12 11:25:29 +02:00
Yueh-Po Peng
8a7b2fa528
Update README.md (#4388)
Fix small typo.
2023-12-10 23:27:38 +01:00
Georgi Gerganov
bcc0eb4591
llama : per-layer KV cache + quantum K cache (#4309)
* per-layer KV

* remove unnecessary copies

* less code duplication, offload k and v separately

* llama : offload KV cache per-layer

* llama : offload K shift tensors

* llama : offload for rest of the model arches

* llama : enable offload debug temporarily

* llama : keep the KV related layers on the device

* llama : remove mirrors, perform Device -> Host when partial offload

* common : add command-line arg to disable KV cache offloading

* llama : update session save/load

* llama : support quantum K cache (#4312)

* llama : support quantum K cache (wip)

* metal : add F32 -> Q8_0 copy kernel

* cuda : add F32 -> Q8_0 copy kernel

ggml-ci

* cuda : use mmv kernel for quantum cache ops

* llama : pass KV cache type through API

* llama : fix build

ggml-ci

* metal : add F32 -> Q4_0 copy kernel

* metal : add F32 -> Q4_1 copy kernel

* cuda : wip

* cuda : add F32 -> Q4_0 and F32 -> Q4_1 copy kernels

* llama-bench : support type_k/type_v

* metal : use mm kernel only for quantum KV cache

* cuda : add comment

* llama : remove memory_f16 and kv_f16 flags

---------

Co-authored-by: slaren <slarengh@gmail.com>

* readme : add API change notice

---------

Co-authored-by: slaren <slarengh@gmail.com>
2023-12-07 13:03:17 +02:00
Georgi Gerganov
05cd6e5036
server : recognize cache_prompt parameter in OAI API (#4347) 2023-12-06 20:21:59 +02:00
Ed Lee
33e171d1e9
server : fix OpenAI API stop field to be optional (#4299)
(cherry picked from commit Mozilla-Ocho/llamafile@e8c92bcb84)
2023-12-03 11:10:43 +02:00
Rickard Edén
6949b50df5
py : add grammar to oai like api (#4294) 2023-12-03 11:03:25 +02:00
Georgi Gerganov
d5a1cbde60
llama : support optional tensors (#4283) 2023-12-01 20:35:47 +02:00
Ziad Ben Hadj-Alouane
1d144112c0
server : add --log-disable to disable logging to file (#4260)
* * add --log-disable to disable logging to file in the server example

* * typo fix
2023-12-01 00:25:49 +02:00
Ziad Ben Hadj-Alouane
f43f09366d
server : add single-client multi-prompt support (#4232)
* * add multiprompt support

* * cleanup

* * more cleanup

* * remove atomicity of id_gen, and change lock_guard to unique_lock on completion requests

* * remove all references to mutex_multitasks

* Update examples/server/server.cpp

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* Update examples/server/server.cpp

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* Update examples/server/server.cpp

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* Update examples/server/server.cpp

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* * change to set

---------

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
2023-12-01 00:25:04 +02:00
rhjdvsgsgks
e2bd725f4b
py : fix oai proxy (#3972)
* fix oai proxy

fix generation not stoped while bot stop talking in chat mode

fix possible `slot_id` not exist

response for cors (and pre flight)

* oai proxy: workaround for some client (such as Chatbox)

* use stop as separator to replace hardcoded `\n`
2023-11-30 22:50:40 +02:00
Georgi Gerganov
af19d35734
server : OAI API compatibility (#4198)
* Add openai-compatible POST /v1/chat/completions API endpoint to server example

* fix code style

* Update server README.md

* Improve server README.md

* Fix server.cpp code style according to review

* server : some style changes

* server : indentation

* server : enable special tokens during tokenization by default

* server : minor code style

* server : change random string generator

* straightforward /v1/models endpoint

---------

Co-authored-by: kir-gadjello <111190790+kir-gadjello@users.noreply.github.com>
Co-authored-by: Tobi Lütke <tobi@Tobis-MacBook-Pro.local>
2023-11-25 11:29:06 +02:00
Haohui Mai
55978ce09b
Fix incorrect format strings and uninitialized variables. (#4133)
* Fix incorrect format strings and uninitialized variables.

* Address comments

* Add the missing include statement
2023-11-23 22:56:53 +01:00
SoftwareRenderer
936c79b227
server : relay error messages (#4131) 2023-11-19 18:54:10 +02:00
Kerfuffle
91f6499393
Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040)
* gguf-py: gguf-dump: Respect --no-tensor flag in JSON mode.

* Respect add_bos_token GGUF metadata value

* gguf-py: Try to fix SpecialVocab giving up too easily for the Nth time
2023-11-16 19:14:37 -07:00
Alexey Parfenov
d96ca7ded7
server : fix crash when prompt exceeds context size (#3996) 2023-11-10 23:48:21 -06:00
Jhen-Jie Hong
4a4fd3eefa
server : allow continue edit on completion mode (#3950)
* server : allow continue edit on completion mode

* server : handle abort case in runCompletion

* server : style improvement
2023-11-10 16:49:33 -06:00
Mihai
57ad015dc3
server : add min_p param (#3877)
* Update server.cpp with min_p after it was introduced in https://github.com/ggerganov/llama.cpp/pull/3841

* Use spaces instead of tabs

* Update index.html.hpp after running deps.sh

* Fix test - fix line ending
2023-11-08 20:00:34 -06:00
Damian Stewart
381efbf480
llava : expose as a shared library for downstream projects (#3613)
* wip llava python bindings compatibility

* add external llava API

* add base64 in-prompt image support

* wip refactor image loading

* refactor image load out of llava init

* cleanup

* further cleanup; move llava-cli into its own file and rename

* move base64.hpp into common/

* collapse clip and llava libraries

* move llava into its own subdir

* wip

* fix bug where base64 string was not removed from the prompt

* get libllava to output in the right place

* expose llava methods in libllama.dylib

* cleanup memory usage around clip_image_*

* cleanup and refactor *again*

* update headerdoc

* build with cmake, not tested (WIP)

* Editorconfig

* Editorconfig

* Build with make

* Build with make

* Fix cyclical depts on Windows

* attempt to fix build on Windows

* attempt to fix build on Windows

* Upd TODOs

* attempt to fix build on Windows+CUDA

* Revert changes in cmake

* Fix according to review comments

* Support building as a shared library

* address review comments

---------

Co-authored-by: M. Yusuf Sarıgöz <yusufsarigoz@gmail.com>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
2023-11-07 00:36:23 +03:00
Thái Hoàng Tâm
bb60fd0bf6
server : fix typo for --alias shortcut from -m to -a (#3958) 2023-11-05 18:15:27 +02:00
cebtenzzre
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
* cmake : fix build when .git does not exist

* cmake : simplify BUILD_INFO target

* cmake : add missing dependencies on BUILD_INFO

* build : link against build info instead of compiling against it

* zig : make build info a .cpp source instead of a header

Co-authored-by: Matheus C. França <matheus-catarino@hotmail.com>

* cmake : revert change to CMP0115

---------

Co-authored-by: Matheus C. França <matheus-catarino@hotmail.com>
2023-11-02 08:50:16 +02:00
cebtenzzre
898aeca90a
llama : implement YaRN RoPE scaling (#2268)
Co-authored-by: cebtenzzre <cebtenzzre@gmail.com>
Co-authored-by: Jeffrey Quesnelle <jquesnelle@gmail.com>
2023-11-01 18:04:33 -04:00
Adrian Hesketh
ca190bca8e
server : re-enable completion and embedded at the same time (#3876) 2023-11-01 11:28:28 +02:00
Kerfuffle
6e08281e58
Extend llama_kv_cache_seq_rm to allow matching any sequence (#3843)
* Extend llama_kv_cache_seq_rm to allow matichng any sequence

* Replace llama_kv_cache_tokens_rm with llama_kv_cache_clear

Use llama_kv_cache_clear for cache clearing

Change calls to llama_kv_cache_tokens_rm that want to delete by position to use llama_kv_cache_seq_rm functionality
2023-10-29 11:31:40 -06:00
Georgi Gerganov
34b2a5e1ee
server : do not release slot on image input (#3798) 2023-10-26 22:54:17 +03:00
cebtenzzre
ad93962657
server : add parameter -tb N, --threads-batch N (#3584) (#3768)
Co-authored-by: Michael Coppola <m18coppola@gmail.com>
Co-authored-by: Michael Coppola <info@michaeljcoppola.com>
2023-10-24 23:10:43 +03:00
Georgi Gerganov
1717521cdb
server : do not block system prompt update (#3767)
* server : do not block system prompt update

* server : update state machine logic to process system prompts

* server : minor
2023-10-24 23:08:20 +03:00
Marcus Dunn
5be6c803fa
llama : remove token functions with context args in favor of model (#3720)
* added `llama_model_token_*` variants to all the `llama_token_*` functions.

* added `LLAMA_API`

* formatting

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* removed old `llama_token` functions

* changed 3 more functions to take in model

- `llama_token_get_text`
- `llama_token_get_score`
- `llama_token_get_type`

* added back docs

* fixed main.cpp

* changed token functions to use new model variants

* changed token functions to use new model variants

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-10-23 22:40:03 +03:00
Georgi Gerganov
438c2ca830
server : parallel decoding and multimodal (#3677)
* implementing parallel decoding in server example

* crash fixed

* save dev progress

* refactored sampling function

* completion endpoint working

* multiple client support

* grammar + no stream completion

* cached prompt support

* chat.mjs support cached prompt + some fixes

* server ui now support multiple clients

* unused change reverted

* fixed timings per slot

* add context swap

* add changes to README.md

* llava multimodal integration

* fixed tokens probs

* add multimodal input - alfa

* refactor code + remove unused comments + improved README.md

* fix compilation errors with llvm

* notify the user from server ui that multimodality is unavialable

* some ci fixes

* fix ci make build undefined ref errors

* fix long prompt than ctx proposed in #3639

* fixed premature end due stop word

* context shift fixed

* fix llava implementation

* sync README.md changes

* readme change

* update api like OpenAI

* multimodal support enabled by default

* fix make bui;d errors

* fix multiple clients

* fix zig build

* new sampling API

* latest changes of sampling API

* server : coding-style normalization

* server : coding-style normalization (part 2)

* server : remove beam-search functionality

* server : bug fix in ingest_images

n_tokens is incremented internally by llama_batch_add

* server : use refs + use llama_batch_clear()

* server : snake case

* server : minor sync

* added thread safe pipeline

* server : bach has to be allocated for n_parallel sequences

* server : no need for atomic int - already using mutex

* server : logs + minor code style

* server : fix multibyte handle in partial response (#3706)

* fix image load + view image in chat

* make : silence stb warnings

* clip : link to ggml, not to llama

* server : fix switch fallthrough

* server : fix crash in Debug on macOS (I have no idea why this fixes it!?)

* server : refactor ctx_sampling init + n_ctx + names

* server : bug fix for prompt caching

* Do not save/load image_data to localStorage

* editorconfig : new line in index.html

* server : completion requests remember slot_id

* Update readme to document multimodal in server

* server : minor style

* Update readme to document multimodal in server

* server : hide ctx_sampling->prev behind API (#3696)

* server : apply fix from #3722

* server : fix slot reuse

* server : add comment about changing slot_state to bool

---------

Co-authored-by: FSSRepo <go778sgt@gmail.com>
Co-authored-by: Damian Stewart <d@damianstewart.com>
Co-authored-by: Steward Garcia <57494570+FSSRepo@users.noreply.github.com>
Co-authored-by: Jhen-Jie Hong <iainst0409@gmail.com>
Co-authored-by: M. Yusuf Sarıgöz <yusufsarigoz@gmail.com>
2023-10-22 22:53:08 +03:00
Georgi Gerganov
d1031cf49c
sampling : refactor init to use llama_sampling_params (#3696)
* sampling : refactor init to use llama_sampling_params

* llama : combine repetition, frequency and presence penalties in 1 call

* examples : remove embd-input and gptneox-wip

* sampling : rename penalty params + reduce size of "prev" vector

* sampling : add llama_sampling_print helper

* sampling : hide prev behind API and apply #3661

ggml-ci
2023-10-20 21:07:23 +03:00
Georgi Gerganov
a0edf73bda
server : fix uninitialized sampling context (close #3685) 2023-10-20 13:06:10 +03:00
Georgi Gerganov
0e89203b51
speculative : add tree-based sampling example (#3624)
* sampling : one sequence per sampling context

ggml-ci

* speculative : add tree-based sampling support

ggml-ci

* speculative : reuse the n_parallel CLI param

* speculative : refactor sampling

* examples : fix build after sampling refactoring

ggml-ci

* batched : fix n_seq_id

* sampling : fix malloc

ggml-ci

* swift : fix build

ggml-ci

* swift : try to fix build

ggml-ci

* prompts : add assistant.txt

* common : add llama_batch_add() and llama_batch_clear() helpers

* speculative : minor refactor

ggml-ci

* minor : comments + rename

ggml-ci

* speculative : fix off-by-one for n_drafted

* speculative : fix the n_drafted fix + p constants
2023-10-18 16:21:57 +03:00
Georgi Gerganov
e74c705e15
editorconfig : remove trailing spaces 2023-10-17 19:52:53 +03:00
coezbek
3ad1e3f1a1
server : documentation of JSON return value of /completion endpoint (#3632)
* Added documentation of JSON return value of /completion endpoint

* Update examples/server/README.md

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-10-17 19:51:02 +03:00
Aarni Koskela
b016596d90
server : add completion mode (no chat) (#3582) 2023-10-12 09:51:53 +03:00
Georgi Gerganov
57dd55e2c7
server : fix kv cache management (#3588) 2023-10-12 09:29:04 +03:00
Michael Coppola
a8bdd65525
server : add parameter -tb N, --threads-batch N (#3584)
Co-authored-by: Michael Coppola <info@michaeljcoppola.com>
2023-10-11 22:42:22 +03:00
Kerfuffle
70c29da118
common : fix mirostat state when using multiple sequences (#3543)
* Fix mirostat state when using multiple sequences

* Fix mirostat by completely refactoring sampling!

* Try to fix zig build.

* Export function to fetch/create default sampler states

Code formatting cleanups and add some comments

Silence a warning about id not being used when logging is disabled

* Apply some renaming suggestions.

Fix comments that were out of sync with the pull.

* Use more consistant naming convention for sampling contexts
2023-10-11 22:35:46 +03:00
vvhg1
11ea5c7d96
infill. : fix tokenization (#3508)
* infill tokens correction

* serverinfill tokens correction

* removing any leading whitespace from infill suffix and removing leeading space token from suffix when params.escape

* removing any leading whitespace from infill suffix and removing leeading space token from suffix when params.escape

* only rm when params.escape, rm space if possible which is added back or rm added space token

* only rm when params.escape, rm space if possible which is added back or rm added space token

* Revert "only rm when params.escape, rm space if possible which is added back or rm added space token"

This reverts commit 63ba0b621f.

* fix interactive prompt escaping and fix server infill leading space handling

* rm unnecessary bool check
2023-10-10 10:31:21 +03:00
Ryder Wishart
8e6716a102
api_like_OAI.py : compat with Microsoft Guidance (#2746)
Check for None in addition to empty string check in all request params

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-10-08 13:55:58 +03:00
arcrank
9c38d181d4
api_like_OAI.py : simplify function (#2796)
Simplify function
2023-10-08 13:52:57 +03:00
Mihai
cb13d73a72
server : docs fix default values and add n_probs (#3506) 2023-10-06 21:39:33 +03:00
Jhen-Jie Hong
97af49fa39
server : reuse llama_sample_token common util (#3494)
* server : reuse llama_sample_token common function

* common : use n_probs for temperature sampling
2023-10-06 15:44:24 +03:00
Kenvix ⭐
45eba9369f
build : use std::make_tuple() for compatibility with older GCC versions (#3488) 2023-10-05 20:16:39 +03:00
Jhen-Jie Hong
e8b8d32e86
server : fix incorrect num_tokens_predicted (#3480) 2023-10-05 17:02:55 +03:00
Georgi Gerganov
ac2219fef3
llama : fix session saving/loading (#3400)
* llama : fix session saving/loading

* llama : temp fix for clearing "future" tokens from the KV cache

* llama : fix handling of "future" tokens when loading sessions

* llama : fix comments for llama_kv_cache API
2023-10-03 21:04:01 +03:00
vvhg1
c97f01c362
infill : add new example + extend server API (#3296)
* vvhg-code-infill (#1)

* infill in separate example (#2)

* reverted changes to main and added infill example

* cleanup

* naming improvement

* make : add missing blank line

* fix missing semicolon

* brought infill up to current main code

* cleanup

---------

Co-authored-by: Cebtenzzre <cebtenzzre@gmail.com>
2023-10-02 10:42:02 +03:00
slaren
16bc66d947
llama.cpp : split llama_context_params into model and context params (#3301)
* llama.cpp : split llama_context_params into model and context params

ggml-ci

* fix metal build

* fix freq_base/scale default to model value

* llama-bench : keep the same model between tests when possible

* move n_threads to llama_context_params, add n_threads_batch

* fix mpi build

* remove kv_size(), cuda scratch fixes

* remove low-vram option

* add n_threads_batch to system info, refactor to get_system_info()

* add documentation about --threads-batch to the READMEs

* llama-bench fix

* main : fix rope freq/scale warning

* llama.cpp : add llama_get_model
common : add llama_tokenize from model

* remove duplicated ctx/model functions

ggml-ci

* cuda : print total VRAM used
2023-09-28 22:42:38 +03:00
xaedes
0e76a8992c
train : finetune LORA (#2632)
* fix track_max_mem in forward_batch_wo_cache_flash_attn_train

* remove unnecessary Adam(W) optimizer tensors.

reduces optimizer memory overhead from 7*modelsize to 2*modelsize.

additionally allows to optimize models with more than 2^31 parameters by replacing int with int64_t.

bumps training checkpoint file version, but old checkpoints can still be read.
new version with less tensors is saved.

* add gradient clipping to AdamW

* Fix reset of unused g->nodes and g->grads to NULL

* implement gradient checkpointing for training

reduces memory overhead from O(n_layer) to O(sqrt(n_layer))

as explained in readme of https://github.com/cybertronai/gradient-checkpointing

* remove unused compute buffer 3

* add and use function ggml_build_backward_expand to avoid stack overflows with large maximum number of nodes

GGML_API void ggml_build_backward_expand(struct ggml_context * ctx, struct ggml_cgraph * gf, struct ggml_cgraph * gb, bool keep);

* change AdamW decay parameter to work like the torch AdamW decay parameter

It is now relative to Adam learning rate `alpha*sched`.
Before that it was relative to `sched` only.

`alpha` being the maximum learning rate and `sched` being a scaling parameter in [0..1]

* change default AdamW weight decay parameter used in training to 0.1 as used in nanoGPT

* change default AdamW weight decay parameter defined in ggml to 0.0, making Adam default instead of AdamW

btw: the default weight decay parameter for torch.optim.AdamW is 0.01

* bug fixes for cross entropy loss

ggml_cross_entropy_loss: sums where not correctly added in workload of each thread
ggml_cross_entropy_loss_back: simplify backward process, reducing numerical issues

guard usage of exp f16 lookup in cross entropy by #define GGML_CROSS_ENTROPY_EXP_FP16

cross entropy loss is only used once during training, but it is quite sensitive to numerical errors introduced by exp-f16-lookup.
so exp-f16-lookup for cross entropy loss is disabled by default, trading better gradients for very slightly worse runtime performance.

* fix test-grad0 for cross_entropy_loss

the second argument to cross_entropy_loss must sum up to 1 for each row

* fix test-grad0 for soft_max

dont use only sum as aggregation, because sum of softmax is always 1 -> finite differences should not work
instead use sum(log(soft_max()*(1-eps)+eps)); use eps to avoid log(0)

* improve finite differences of test-grad0 by using double instead of float

* change cross_entropy_loss to output average over all rows

this helps keeping the loss and gradients in a sane range

* improve gradient checkpointing

sqrt(n_layers) is only the best checkpoint step when mem size of checkpoints and mem size of layers are equal.
since layers require more memory than the single-tensor-checkpoint we use, the optimal values are compute different:

```
  given: n, u, v
  objective: minimize(a*u+b*v) where a*b=n, a>0, b>0
  b=n/a
  minimize(a*u+v*n/a)
  diff(a*u+v*n/a, a) = u - (v*n/a)/a
  diff(a*u+v*n/a, a) == 0
  u - (v*n/a)/a == 0
  u == v*n/(a*a)
  u*a*a = v*n
  a*a = v*n/u
  a = sqrt(n*v/u)
```

this change results in more checkpoints, requiring less layers to store between checkpoints, overall improving memory usage.

* disable gradient checkpointing debug output

* llama : fix rope usage in train-text-from-scratch after ChatGLM change

* add more training parameters:

--enable-restart N         Only for Adam optimizer. Enable restarts of cos-decay
--disable-restart N        Only for Adam optimizer. Disable restarts of cos-decay
--opt-past N               Number of optimization iterations to track for delta convergence test. Disabled when zero.
--opt-delta N              Maximum delta for delta convergence test. Disabled when <= zero.
--opt-max-no-improvement N Maximum number of optimization iterations with no improvement. Disabled when <= zero.
--adam-epsf N              AdamW epsilon for convergence test. Disabled when <= zero.
--adam-min-alpha N         Adam minimum learning rate alpha, usually 0.1 * alpha

* replace memcpy with reshape operation so that the graph is not cut at the input

this makes it possible to store other values into the input tensor and then simply recompute the graph without rebuilding it

* remove unused function argument from get_example_targets_batch

* measure and print total training time

* add optimization callback to ggml_opt_resume_g

this callback is called before each iteration with custom data and pointer to learning schedule parameter (only used in Adam(W)).

can be used for dynamic learning schedule and setting input data for batches before each iteration

* use optimization callback in training

allows dynamic learning schedule and different batch data for each iteration without relying on low n_iter and high n_examples parameters

reduces runtime by avoiding restart of optimization function and improves training convergence by providing a different batch for each iteration

* add minimum number of tensor dimensions to apply weight decay (default 2)

this allows to not apply weight decay to bias parameters

* rename training parameter cos-decay-alpha to cos-decay-min and clarify that adam-min-alpha also applies to warmup

* fix increase of model.train_samples and model.train_tokens

now that each optimizer iteration gets its own batch we need to multiply by number of opt iterations

* change sampling parameters for prediction after training to defaults of common.h

and clarify what is context for prediction and what are generated tokens

* tighten abs error bounds for cross_entropy_loss in test-grad0

* add conditional compilation of using F16 exp in flash attention

uncomment `// #define GGML_FLASH_ATTN_EXP_FP16` to enable usage of f16 exp in flash attention

* tighten abs error bounds for flash_attn in test-grad0

* tighten abs error bounds for sqrt in test-grad0

* remove out-commented vectorized code of opt_adam

the vectorized code might be bit faster for low number of parameters, but it had a big memory usage overhead

* ggml : update ggml_rms_norm_back with configurable eps

* llama training : fix ggml_rms_norm_back calls to pass configurable eps

* remove trailing whitespace

* add train function using automatic gradient checkpointing backward pass and allocator

* in train function replace add_inplace by regular add

because using add_inplace seems to result in different gradients

* don't use allocate hash_map on context

because the context has no_alloc=True when using memory allocator resulting in NULL data pointers

* correctly clone reshape and permute operations by also cloning tensor->nb values

* fix variable name and add missing type cast

* terminate recursive tensor cloning when reaching tensor without src tensors

* correctly clone view tensors by setting data pointers

without this the checkpointing would only work when being used together with memory allocator

* fix variable names

* swap arguments to commutative ops to be the same as in `forward_batch_wo_cache_flash_attn`

* add input tensors as checkpoints

so that recursive tensor cloning of gradient checkpointing terminates on input tensors

* fix variable name and add missing boolean negation

* make sure some tensors are not reallocated by inserting new temporary nodes depending on them:

output and parameter gradient tensors need to be available at the end of the graph execution

parameter gradient tensors also need to be available before the graph execution because they are set to zero before each optimizer iteration

checkpoint tensors are allocated all together to reduce memory allocator fragmentation

afterwards, in addition to the temporary nodes, we also need to reset the temporary leafs

* fix ASSERT to work with zero layers

* add training options whether to use allocator and/or unified training function

* integrate unified training function which may use memory allocator

the unified training function also supports arguments whether to use flash attention and/or gradient checkpointing

* format name of cloned tensors with " (clone)" suffix

* set names for tensors in unified train function for easier debugging

* allocate graph on context using ggml_new_graph

* remove handwritten training functions

* remove unused training parameters "use_scratch" and "use_unified"

* remove trailing whitespace

* remove unused train params: mem_compute1_gb & mem_compute2_gb

mem_compute_gb is used for compute when automatic memory allocator is not enabled, otherwise it can be very small to only hold the tensor definitions
mem_compute0_gb is used for automatic memory allocator (as long as measurement of max required size is not implemented)

* remove unused forward_batch function

* add debug asserts in ggml_allocr_alloc to some common pitfalls when using this function directly

* only use ggml_allocr_alloc when tensor has NULL data and is no view

* fix test when to create temporary backward graph

temporary backward graph is only necessary when using checkpointing

* fix memory "leak" in optimizers

each iteration a new cplan with new memory for work data was allocated.
now cplan creation only happens at the start of optimization, with each iteration reusing the cplan and its work data.

* reverse order of for loop in ggml_build_backward_expand to save memory when using gradient checkpointing and allocator

with this loop order gradient checkpointing with allocator on 16 layer model saves 13% memory; 2 layer memory it saves 2% memory.

the computation results are the same

* add API functions to access llama model tensors

* add stub example for finetuning, based on train-text-from-scratch

* move and remove code

* add API functions to access remaining model parameters:

mult, head and rot

* first draft for LORA finetune training

* remove const model and layer arguments in API functions for accessing model tensors

* bug fixes to make finetune compile

automatic allocator does not work yet

* add debug prints for training memory improvements

* fix names of lora tensors

* avoid stack overflow resulting from big ggml_cgraph

replace stack allocation and ggml_build_forward by ggml_new_graph in combination with ggml_build_forward_expand

* replace llama API functions to get model tensors by one function to get model tensor by name

LLAMA_API struct ggml_tensor * llama_get_model_tensor(struct llama_model * model, const char * name);

* remove unused call to not existing llama_get_layer_from_model

* implement ggml_compute_forward_out_prod_q_f32

* remove trailing whitespace

* add lora finetune support on quantized base model tensors

* add ggml_add_cast API function

this function works like ggml_add, but accepts a data type for the resulting tensor.
only supported for quantized src0 input.

* use ggml_add_cast in finetuning

lora-applied weights will now have data type F32, which improves gradients when finetuning quantized base models

* bug fix: actually use result type passed to ggml_add_cast

* make sure base model tensors data cannot be used in viewable operations

memory allocator would try to make lora application inplace on base model tensors.
since those are memory mapped this will result in memory access violations

* fix bug in ggml_out_prod which resulted in wrong n_dims of result tensors

* avoid keeping in memory ALL of the gradients

The problem here stems from ggml_graph_reset. This function is called in the optimization function, before each graph computation, to reset the gradients to zero. This required a unique memory slot for each gradient: allocating memory from a previosly freed memory location might lead to non-zero input gradients.

During ggml_compute_backward the gradients are build stepwise by adding or substracting new values, starting from a OP_NONE tensor which needs to contain zero-values. This requires the graph reset.

To avoid this I now remember in ggml_build_backward_expand the original OP_NONE gradient tensors in a hash table, which is passed to ggml_compute_backward. There instead of using add (or sub or similar) I test whether the existing gradient to be changed is a zero-valued-tensor by looking up its existence in the hash table. When it is such a zero-tensor it will not be modified, but replaced by the value to be added, otherwise the regular add (not inplace, allocator will take care of this) will be used. This way none of those zero-tensor values will be necessary in the final backward graph and more importantly they won't need a unique memory slot, just to make them zero.

* remove trailing whitespace

* remove debug prints and function to compute tensor data hash

* improve optimization iteration prints

* adjust maximal values to support finetuning 3B models

* change default finetune params lora_r and lora_alpha to match the n_rank parameters of 4

* bug fix: make sure finetune input gradient is allocated at begin and kept until end

* remove unnecessary src tensor from ggml_get_rows_back

we don't need data of src[2] for computation, only to setup the correct output shape.
remove dependency on src[2], so that allocator can work more freely.

the computational graph is still completely determined, because the output shape is naturally included.
this is similar to how ggml_reshape does it.

* remove unnecessary src tensor from ggml_repeat & ggml_repeat_back

we don't need data of src[1] for computation, only to setup the correct output shape.
remove dependency on src[1], so that allocator can work more freely.

the computational graph is still completely determined, because the output shape is naturally included

* resolve todo

allocator will only make it inplace when they are of the same type

* mixing multiple LORA adapters is now possible

pass more than one '--lora FNAME' argument to apply more than one LORA.
use '--lora-scaled FNAME S' when you want to specify a user-defined scale for an adapter.

* add option to save finetune output every N iterations

* also save latest finetune output with ITERATION="LATEST" and print where files are saved

saving with LATEST makes it easier to resume training from the latest checkpoint
the string "LATEST" can be configured with command line option "--fn-latest STR"

* update checkpoint train stats before saving via "--save-every"

* add command line option `--rank-wo N` for rank of wo tensor

* update finetune README

* fix dump_non_result_info_yaml to output multiple lora adapters

* bug fix: replace GGML_TYPE_SIZE[t] by ggml_type_size(t)

* replace llama_n_mult by llama_n_ff

* finetune bug fixes to compile with merged in code from master

* remove prediction related code to reduce duplicated code with main

use main instead

* reduce large memory overhead in train-text-from-scratch

all gradients had to be pinned so that graph_reset works correctly.
this is no longer necessary with the changes to ggml_compute_backward introduced in this PR.

* add comment explaining why finetune checkpoints are allocated in one block

* make default value of float member a float literal

* handle rms_norm and rope parameters the same as in train-text-from-scratch

* remove unused code

* remove vocab related code as it is unnecessary

* add LLM_KV_TRAINING_TYPE to train-text-from-scratch checkpoints

so that they can be differentiated from lora finetune checkpoints

* add gguf constants and load/save functions from train-text-from-scratch

* add load & save lora finetune checkpoints via gguf

* add python script to convert old finetune checkpoint files to gguf

* remove old checkpoint save & load code

* remove code to print data checksums which was used to verify correctness of new gguf code

* omit tokenization when training is disabled, only save llama lora adapter

training can be disabled by passing '-n 0' to finetune

* remove trailing whitespace

* update README.md

* implement ggml_compute_forward_repeat_f16

* avoid stack overflow of large cgraphs in test-grad0

* add ggml API functions ggml_unravel_index, ggml_get_i32_nd and its analogs for set and for f32

ggml_get_i32_1d, ggml_set_i32_1d, ggml_get_f32_1d, ggml_set_f32_1d now support non-contiguous tensors.
in case of non-contiguous tensor, the 1d index is unraveled into a multi index using ggml_unravel_index to be passed to '_nd' function equivalent.

this fixes a bug in test-grad0 which happens due to ggml_build_backward not building purely contiguous tensors anymore

* increase test-grad0 context mem size to accommodate for bigger cgraph

* add sanity check to ggml_compute_backward, asserting the correct shape of gradients

* fix ggml_acc_or_set to return tensor of correct shape

* remove unused 'inplace' argument from ggml_compute_backward function

inplace operations to add gradients are no longer created by ggml_compute_backward
use allocator to automatically make inplace operations

* add missing argument 'int i0' to ggml_get_i32_nd & ggml_set_i32_nd header declarations

* fix error message in ggml_allocr_alloc to display actual max_avail

* fix check_gradient

ggml_build_backward_expand was previously replaced by ggml_build_backward, but the assignment of forward graph to backward graph missing

* use tensor->view_src instead of ggml_is_view and get_view_source

* move gradient checkpointing code into ggml, new API function:

// build gradient checkpointing backward graph gb for gf using provided checkpoints
// gb_tmp will contain original backward graph with rewritten backward process nodes,
// but without the second forward pass nodes.
GGML_API void ggml_build_backward_gradient_checkpointing(
        struct ggml_context   * ctx,
        struct ggml_cgraph    * gf,
        struct ggml_cgraph    * gb,
        struct ggml_cgraph    * gb_tmp,
        struct ggml_tensor  * * checkpoints,
        int                     n_checkpoints);

* replace custom data getters and setters by ggml functions

* train-text-from-scratch can train (full finetune) gguf models

just pass the gguf model via `--checkpoint-in FN`.
after this, to continue training, pass the generated checkpoint instead of the original gguf model.

tested with smaller models, bigger models may exceed available memory.
use (LORA) finetune for those.

* remove trailing whitespace

* add option to save train-text-from-scratch output every N iterations

* update README.md

* fix warnings

* fix warnings

* remove finetune option to disable allocator

the allocator should always be used.
by making sure that it is always used it gets easier to implement automatic memory requirements computation

* add tensor checkpoints only when gradient checkpointing is enabled

* initialize opt ggml context if none was provided

* add ggml-alloc API function 'ggml_allocr_max_size' to get max size of alloc

GGML_API size_t ggml_allocr_max_size(struct ggml_allocr * alloc);

* finetune: automatically allocate all memory and changes to command line options

remove '--n_examples N' parameter, as it no longer makes sense to call optimization process multiple times in a loop.
add '--only_write_lora' command line option: will skip tokenization and training, to only write a llama.cpp comptabile LORA adapter.
remove memory buffer related command line options.
improve iteration console output.

* add finetune to Makefile

* update README.md

* print time per iteration and estimate remaining time

* increase measured alloc size by tensor_alignment

ggml_allocr_reset will reduce the given size by up to tensor_alignment-1

* fix README.md

* add some more allocator debug prints

* bug fix, probably solves the 'ggml_allocr_alloc: not enough space in the buffer' issue

* revert last commit

"bug fix, probably solves the 'ggml_allocr_alloc: not enough space in the buffer' issue"

"alloc was freeing an externally allocated tensor, because it calculated the end of allocator memory as alloc->data + alloc->max_size instead of alloc->data + alloc->size."

This is intentional to reduce the risk of freeing external tensors when measuring. Unless max_size is not properly calculated, I don't see why this is an issue.

* remove unnecessary "0x" before "%p" output

* move measurement memory segment to upper region of the address space

* update README.md

* fix printf format warnings

* add missing gguf_free in load_checkpoint_lora_file

* load default rms_norm and rope parameters from base model

* add gradient accumulation

specify number accumulation steps with '--grad-acc N'.
this will simulate a bigger batch size of grad_acc*batch.

* fix tracking of train_samples and train_tokens

* build : fix compile warnings

* ggml : fix L-BFGS linesearch loop

* improve finetune time measurement

fix printf warnings on system where int64_t is (long int).
change time datatypes to double because values get big with long training times.
exclude file saving from time measurement.
converge faster to actual time per iteration by removing very small first duration before first iteration was performed.
fix bug in output of total training time, the reported value was 1000 times to small.

* specify default lora rank with '--lora-r N'

'--lora-r N' will specify default rank for all tensors
'--rank-wq N', etc. will override this default rank for specific tensor types.

* fix gradient accumulation bug where the same batch was used for each microstep

* fix gradient accumulation bug where the same batch was used for each microstep

* support grouped-query-attention in ggml_flash_attn and ggml_flash_attn_back

k and v can now be repeated in q along ne[2]

in forward pass just use modulo to compute k and v indices, like ik2 = iq2 % nek2.

in backard pass this won't work as easy, because multiple threads will compete to accumulate to the same k->grad[:,ik1,ik2,ik3] and v->grad[:,iv1,iv2,iv3].
so we change the parallelization over q rows to be over k rows. this ensures non-overlapping (ik2,ik3) across threads.
in each thread we then iterate over the number of repetitions of k/v in q to compute iq2 as iq2 = ik2 + irep*nek2.

since ne2 is not the same for q,k and v we also change how the gradients are concatenated into the result tensor.
additionally the offsets of gradq, gradk and gradv in the result tensor are now memory aligned.

we also simplify the compute_backward part of flash_attn to use ggml_reshape instead of switching over the number of dimensions.
this needs a small change to ggml_reshape, removing the assertion of second argument to be contiguous.
since only the shape (ne) of the second reshape argument is of relevance, its memory layout (nb) is irrelevant -> it can very well be non-contiguous.

change test-grad0 to also test for repeated k/v in q.

this changes the rng and now results in small gradient differences in softmax. these solely come from using f16 exp table lookup in forward softmax: when temporarily changing softmax to use actual exp function, the reported gradient differences go away. gradient differences coming solely from f16 table lookup are acceptable.
added a note to explain this.

* add llama API functions to get grouped-query-attention n_head parameter 'n_head_kv'.

* fix finetune to support grouped-query-attention (using flash-attention)

note: ggml changes to ggml_out_prod are necessary to support grouped-query-attention without flash-attention.

* support broadcastable a in out_prod(a, b) and backward pass of broadcasting mul_mat(a, b)

* test broadcasting mul_mat backward pass

* decouple random number generator of each operation test

when changing one test the rng of others tests is not influenced anymore

* add comment briefly describing what ggml_repeat_back does

* simplify broadcasting mul_mat backward using ggml_repeat_back

* add cgraph evaluation order member and corresponding enum type

this controls in which order ggml_build_forward visits source nodes.
by default the nodes are visited left to right, i.e. src[0] first.
in some cases it is beneficial for ggml-alloc to visit in a different order.
two possible orders are supported: left-to-right (src[0] first) and right-to-left (src[0] last).

* measure max compute size for each cgraph eval order and use best order

this can bring huge memory savings:
e.g. codellama-34b with n_ctx=64, n_batch=1 goes from 92927.8mb down to 4627.6 MB

* remove unused command line options

* add sample start patterns and options to force new or by default resume last shuffling

* update shuffle rng state on reshuffle

* exclude known zero values from computations in flash_attn_f32 & flash_attn_back_f32

* remove probably unnecessary exception type flags from stringstream

* pass correct max number of tokens to llama_tokenize

* account for possible leading whitespace that will be added by tokenizer
e.g. '\t' will be tokenized by llama spm tokenizer to [29871, 12]

* use unrolled vec_mad in out_prod

y is vec_mad result vec.
x is vec_mad input vec.
v is vec_mad input scalar.

ggml_vec_mad_f32_unroll will internally loop over x and v with same y.

GGML_VEC_MAD_UNROLL is by default defined to 32.

This value is empirical optimized using performance test runs of out-prod in openllama-3b finetune with 256 context length and batch size 1. It gives 23% performance boost for out_prod.

Full measurements of out-prod runtime in ms:
	unroll_xv	unroll_yv
1	67014.643	87826.469
2	77117.552	89077.656
4	72091.311	109121.657
8	61077.543	88678.334
16	56914.67	79514.947
24	59024.595	84350.254
28	55952.446	83368.73
32	51476.658	85177.745
36	55973.792	84659.92
40	55139.616	93844.738
48	60736.392	93330.267
64	99856.878	116994.99

Second column is when unrollying yv instead of xv

* set lora_alpha to value of lora_r if it is not set via command line

otherwise only changing lora_r will change scaling of lora adapter used in prediction

* reshuffle original sample order instead of the previous shuffled order

otherwise resumed reshuffle will not result in same sample order

* block tiling for out-prod inspired by mul-mat

block sizes are empirically optimized

roughly doubles the flops of out-prod

* exclude some more known zero values from computations in flash_attn_f32 & flash_attn_back_f32

* add static keywords

* remove outcommented old code

* update train-text-from-scratch with tokenization, sample selection and shuffling from finetune

* remove lbfgs related train parameters

* move common train functions into common/train.[h|cpp]

* move train state into struct train_state

* move train data saving code into callback to unify code of opt_callback

train_params are still different in finetune and train-text-from-scratch, so it can't yet be moved to train.h|cpp

* move common train params into common/train

* move common opt_callback into common/train

* fix consume_common_train_arg

* save and load head_count_kv in lora checkpoints

* increase train_samples by used_samples instead of number of batches

on batch can contain more than one sample when option "fill_with_next_samples" is used

* fix usage of llama_tokenize

* remove static from process_escape since we need it exposed in header

* fix code formating of long function declarations

* fix condition in load_train_state_gguf

* use die("msg") instead of replace GGML_ASSERT(!"msg") or throw std::runtime_error("msg")

* fix saving and loading of training type

* remove terminating '\0' from tokenization

(llama_tokenize is now passed the string length instead of relying on terminating '\0')

* fix compile warnings

* fix compile warnings

* use new/delete for train_state instead of malloc/free

using malloc may result in seg faults when trying to assign string fields

* assert that sample_count > 0, avoiding division by zero

* fix frand to return value in interval [0,1)

* add train option "--sample-random-offsets"

Use samples beginning at random offsets.
The offset is only applied to the first sample in each batch context window.
Together with "--fill-with-next-samples" this may help for training endless text generation.

For example given a dataset containing samples "abcd", "ABCD", "0123".
With context size of 8 and options "--fill-with-next-samples", "--no-separate-with-eos", "--no-separate-with-bos",
the context windows of batches could only be filled with "abcdABCD", "ABCDabcd", "0123abcd", etc.

With "--sample-random-offsets" it can also be filled with "23abcdAB", "bcd0123A", etc.

* deduplicate code into function

* remove n_rot hparam, as it must always be hparam.n_embd_head()

* align code

* assert correct base model tensor shapes

* move some params from lora hparams into model hparams and load model params from gguf

this equalizes the model definition in finetune and text-from-scratch and removes the need for additional llama api functions to get model parameters

* remove now unnecessary llama API functions to get model params that where added by this PR

* train-text-from-scratch: automatically allocate model tensors, remove option '--mem-model N'

* train-text-from-scratch: automatically allocate opt context

* train-text-from-scratch: automatically allocate input tensors

* train-text-from-scratch: automatically allocate compute memory

* remove unused options and equalize train-text-from-scratch with finetune

* initialize opt->loss_after with zero

* add export-lora program

* remove trailing whitespace

* add export-lora build in Makefile

* remove unused struct tensor_info from export-lora

* add export-lora build dependency to llama

because it depends on common, which depends on llama

* update finetune README.md

* cancel optimization when specified number of epochs is completed

* improve handling of export-lora arguments

print errors and warnings when files could not be read or created

* Fix export-lora.cpp "not enough space in the context's memory pool" (#1)

* Fix export-lora.cpp "not enough space in the context's memory pool"

Without this patch, export-lora would sometimes error with "not enough space in the context's memory pool (needed 656784, available 656800)".

* increase required context size by 5*GGML_MEM_ALIGN instead of plain 16

---------

Co-authored-by: xaedes <xaedes@gmail.com>

* improve handling of not yet supported tensor types

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: meatbag-18a <145869052+meatbag-18a@users.noreply.github.com>
2023-09-28 21:40:11 +03:00